Last active
July 29, 2023 10:15
-
-
Save mike-at-redspace/5aece765a9b0cca64d7c347c24b9f6af to your computer and use it in GitHub Desktop.
Client-side scrape Cast from IMDB
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
// https://www.imdb.com/title/tt1865740/fullcredits | |
const collectData = () => { | |
try { | |
const data = { cast: [], crew: [] }; | |
const fullCredits = document.getElementById('fullcredits_content'); | |
for (const child of fullCredits.children) { | |
if (child.classList.contains('simpleCreditsTable')) { | |
for (const row of child.rows) { | |
const [nameCell, , creditCell] = row.cells; | |
const name = nameCell.querySelector('a').textContent.trim(); | |
const credit = creditCell.textContent.trim(); | |
data.crew.push({ name, credit }); | |
} | |
} else if (child.classList.contains('cast_list')) { | |
const photos = document.querySelectorAll('.cast_list .primary_photo a'); | |
const nameCells = document.querySelectorAll('.cast_list .primary_photo + td a'); | |
const characterCells = document.querySelectorAll('.cast_list .character'); | |
for (const [i, photo] of photos.entries()) { | |
const name = nameCells[i].textContent.trim(); | |
const character = characterCells[i].textContent.trim(); | |
data.cast.push({ | |
name, | |
photo: photo.href, | |
character | |
}); | |
} | |
} | |
} | |
return data; | |
} catch (error) { | |
console.error(error); | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment